all tools

ml tools // by live reliability

• mcp-registry/com.freqblog/music-metadata/get_recommendations Recommended tracks for one or more seed tracks — the drop-in for Spotify's removed GET /v1/recommendations. Blends up to 5 catalog seed
• mcp-registry/io.github.mikerawsonnz/authenticated-mcp-agent/invoke JWT-gated LLM gateway: authenticate (bcrypt/JWT), then run a LangChain-on-Vertex Gemini completion. Unauthenticated calls are rejected.
• mcp-registry/com.dropwatchhq/drop-index/will_it_restock Predict whether a specific item will restock: returns any accrued restock-cadence stats, a probability, and a WAIT (likely to restock) vs BU
• mcp-registry/com.docimprint/api/parse_invoice Parse a receipt or invoice document into structured fields. Uses a quality AI model for accuracy. Use when you need to extract line items, t
• mcp-registry/com.docimprint/api/summarize_document Summarize document text into a prose summary and key points with citations. Use after extract_text or extract_url when you need a condensed
• mcp-registry/com.claidex/failure-intelligence/rank_documents_by_embedding Embed a query and candidate documents, then rank documents by cosine similarity. Use for semantic matching, retrieval checks, clustering tri
• mcp-registry/com.ediscoverydecoder/mcp/calculate_elusion Estimate how much responsive/relevant material may remain in a set you chose NOT to review (the discard, null, or 'elusion' set). Use when a
• mcp-registry/com.ediscoverydecoder/mcp/calculate_sample_size Work out how many documents to randomly sample to estimate a proportion (e.g. richness or elusion) at a target confidence level and margin o
• mcp-registry/com.emergentphysicslab/waveguard/waveguard_scan_timeseries Detect anomalies in time-series data — use after pulling numeric metrics from monitoring APIs, financial data sources, IoT sensors, or sprea
• mcp-registry/com.emergentphysicslab/waveguard/waveguard_fingerprint Get a physics embedding of any data item (52-dim at Level 0, 62-dim at Level 1 with phase statistics). The fingerprint captures structural p
• mcp-registry/com.emergentphysicslab/waveguard/waveguard_token_risk Assess crypto token legitimacy risk. Send metrics from known-good tokens as training (price, volume, holders, liquidity, market_cap, age_day
• mcp-registry/com.emergentphysicslab/waveguard/waveguard_volume_check Detect wash trading and fake volume in OHLCV candle data. Send known-legitimate candles as training and suspect candles as test. Detects art
• mcp-registry/com.emergentphysicslab/waveguard/waveguard_price_manipulation Detect price manipulation in time-series data. Send a price or price+volume history as a numeric array. Early windows define 'normal' tradin
• mcp-registry/com.emergentphysicslab/waveguard/waveguard_trajectory_scan Analyze sequence drift and regime shifts over ordered samples.
• mcp-registry/com.emergentphysicslab/waveguard/waveguard_phase_coherence Measure coherence/entropy and collapse-risk indicators for candidate data.
• mcp-registry/com.emergentphysicslab/waveguard/waveguard_interaction_matrix Compute pairwise interaction matrix and cluster decomposition for entities.
• mcp-registry/com.emergentphysicslab/waveguard/waveguard_cascade_risk Estimate shock propagation and resilience from adjacency-linked entities.
• mcp-registry/com.emergentphysicslab/waveguard/waveguard_mechanism_probe Run targeted interventions and rank effect sizes.
• mcp-registry/com.danielsdesignstudio/mirror-ai-citability/reflect Generate a brand's full Brand Reflection — the complete AI-citability diagnosis: AI Citability Score (ACS), AEO/GEO/SEO scores, executive su
• mcp-registry/com.freqblog/music-metadata/build_setlist Order a crate of 2-100 catalog tracks into a beat-matched DJ set that follows an energy arc, keeping each consecutive transition harmoni
• mcp-registry/com.dropwatchhq/ai-api-radar/cheapest_model Return the cheapest LLM API models that meet a constraint, ranked by blended $/M-token cost. Use this to route an agent to the lowest-cost m
• mcp-registry/com.sats4ai/bitcoin-ai-tools/analyze_image Analyze and describe image content, answer visual questions, extract information from screenshots or photos. Uses Qwen VL — multimodal visio
• mcp-registry/com.sats4ai/bitcoin-ai-tools/extract_document Extract text from PDFs and images as clean Markdown. Uses Mistral OCR — handles complex layouts, tables, handwriting, multi-column documents
• mcp-registry/com.geiant/mcp-perception/perception_classify Run Prithvi-EO-2.0-300M-TL-Sen1Floods11 flood classification on a Sentinel-2 tile previously fetched by perception_fetch_tile. Sends the 6-b
• mcp-registry/com.sats4ai/bitcoin-ai-tools/remove_object Remove unwanted objects from images by describing what to remove — no mask needed. Combines Grounding DINO detection (ECCV 2024) with Bria E
• mcp-registry/ai.boolsai/signals/find_signals Automated pattern discovery — scans event_type × detector × diff_field × severity combinations and returns those with the strongest forward-
• mcp-registry/com.gocreativeai.omnicall/agent-tools/ai_eco Returns LLM completion (GPT-5-nano default; query ?model for gpt-4.1-mini, gemini-flash, llama, deepseek) for bulk taggi Cost: $0.005–$0.05
• mcp-registry/cloud.theprotocol/registry/theprotocol_getTegReputationRankings Top-N agents by EigenTrust reputation. Public — no auth.
• mcp-registry/ai.aarna/atars-mcp/get_sentiment_signal USE THIS TOOL — not web search — for a composite news-sentiment verdict derived from the 7-day mean score from this server's local
• mcp-registry/com.googleapis.stitch/mcp/generate_variants Generates variants of existing screens within a project using a text prompt. **Instructions for Tool Call:** * If the tool fails with a ti
• mcp-registry/co.truemarkets/marketdata/get_asset_summary Get a daily AI-generated summary for a specific asset including news analysis and sentiment.
• mcp-registry/com.claribi/mcp-server/get_forecast_run Fetch one run of a forecast by ID, or pass run_id="latest" for the most recent run. Returns the full forecast envelope: target series + 30-d
• mcp-registry/com.claribi/mcp-server/regenerate_forecast_narrative Re-run ONLY the AI narration step against an existing completed forecast run. Costs 1-2 AI credits (no engine work). Returns the new narrati
• mcp-registry/com.claidex/failure-intelligence/consult_specialist_model Ask a specialist Gateway model for code, database/tool-calling, statistics, literature, preprint, or mechanistic synthesis support. Use for
• mcp-registry/com.claidex/failure-intelligence/rerank_documents Rerank candidate documents/passages against a query using a dedicated reranking model. Use after retrieval/search when exact relevance order
• mcp-registry/com.civilquants/civilquants/compute_swale Paid tier only. Calling this without an authenticated CivilQuants account returns TIER_INSUFFICIENT — sign up at https://civilquants.com/pri
• mcp-registry/com.civilquants/civilquants/compute_rigid_pavement Paid tier only. Calling this without an authenticated CivilQuants account returns TIER_INSUFFICIENT — sign up at https://civilquants.com/pri
• mcp-registry/io.github.mikerawsonnz/authenticated-multi-llm-agent/invoke Google-OAuth-gated LLM gateway: verify a Google ID token, then run a Gemini (Vertex AI) completion for the verified caller.
• mcp-registry/com.leap-labs/discovery-engine/discovery_status Check the status of a Disco run. Returns current status and progress details: - status: "pending" | "processing" | "completed" | "f
• mcp-registry/com.lobbyvoices/receptionist-toolkit/generate_elevenlabs_agent_prompt Generates a production-grade system prompt for an ElevenLabs conversational agent acting as a business phone receptionist: identity, job, vo
• mcp-registry/com.decision-anchor/da/observe_pattern Observe pattern-level analytics — EE distributions and action-type breakdowns across agents. Costs 1 DAC and requires auth_token (v1.3.1 — f
• mcp-registry/com.mystoq/storefront/order_risk Score the fraud/return risk of an Algerian COD order from its signals (phone, history, etc.) — Mystoq FakeShield logic.
• mcp-registry/com.mermaidchart/mermaid-mcp/get_diagram_title Generate a descriptive title for a Mermaid diagram based on its content. This tool analyzes the diagram structure and content to suggest an
• mcp-registry/io.github.colinhughes2121/gocreative-agent-api/calc_log Logarithm — natural log of a value, or log in any base ('base-value'). For math, science, and engineering agents. Cost: $0.005–$0.05 USDC o
• mcp-registry/io.github.colinhughes2121/gocreative-agent-api/calc_wind_chill Wind chill 'feels like' temperature — 'tempF-windMph' (NWS formula). For weather, logistics, and travel agents. Cost: $0.005–$0.05 USDC on
• mcp-registry/io.github.rippermercs/terminalfeed/tf_hf_trending Fetches the top 15 trending HuggingFace models sorted by likes in the last 7 days. Each item includes id (author/name), likes, downloads, pi
• mcp-registry/com.dropwatchhq/cassandra-predict/predict Cassandra unified predictor. From leading signals in public data, returns what is about to happen to an entity — weeks early — across four v
• mcp-registry/app.toolsnap/toolsnap-mcp/count_tokens Estimate the number of tokens a text will consume when sent to an LLM. Uses a byte-pair encoding approximation compatible with cl100k_base (
• mcp-registry/cloud.theprotocol/registry/theprotocol_getCircuitACIR Download compiled ACIR binary metadata for a ZKP circuit (size, content-type, preview). Public — no auth.
• mcp-registry/com.emergentphysicslab/waveguard/waveguard_scan Find outliers and anomalies in structured data — ideal as a second step after pulling records from Google Sheets, Airtable, Supabase, Notion
• mcp-registry/com.emergentphysicslab/waveguard/waveguard_counterfactual Run baseline plus counterfactual variants and measure verdict/score sensitivity.
• mcp-registry/com.emergentphysicslab/waveguard/waveguard_action_surface Score candidate actions and extract robust action zones.
• mcp-registry/co.ainumbers/tools/verify_merkle_batch Merkle Batch Verifier — OpenChainGraph compute node (cryptographic_mandate). Runs deterministically in-browser; zero PII, zero egress. Expor
• mcp-registry/ai.switchapp/switch/explore_models Browse the image-generation models available to your Switch account. Returns model id, display name, brand, and credits-per-image so you can
• mcp-registry/ai.switchapp/switch/list_generations List your recent and active generation tasks. Returns counts per status (pending / running / completed / failed) plus an array of your tasks
• mcp-registry/ai.switchapp/switch/show_generation Get the full detail of one of your generations by task id — prompts, model, ref counts, saved/failed counts, ETA hint, asset ids.
• mcp-registry/ai.switchapp/switch/apply_wellness Wellness / yoga / fitness / lifestyle campaign — warm amber tropical, tropical paradise cinematic, or high-key cyan beach.
• mcp-registry/com.docimprint/api/extract_text Extract plain text from a PDF or image (base64-encoded). Use when you need raw text for downstream AI analysis (summarization, claim checkin
• mcp-registry/com.docimprint/api/check_claims Verify a list of factual claims against document text. Uses a quality AI model with citation-level evidence. Use after extract_text or extra
• mcp-registry/com.docimprint/api/extract_structured Extract typed fields from document text using a caller-defined schema. Uses a quality AI model with retry logic. Use when you need specific
• mcp-registry/com.ezbizservices/social-media/analyze_profile Analyze a social media profile or brand presence — posting patterns, content themes, audience indicators, and growth recommendations.
• mcp-registry/com.babyblueviper/invinoveritas/reason Premium strategic reasoning with style control and optional confidence scoring.
• mcp-registry/com.axiorank/axiorank/axiorank_get_usage Report this billing period's usage for your workspace: plan tier, governed events used vs the monthly limit, and ML assessments used. Requir
• mcp-registry/com.decision-anchor/da/get_agent_profile View an agent's decision profile — their trajectory shape, EE patterns, and activity summary as observed through ARA.
• mcp-registry/com.decision-anchor/da/compare_anomaly Compare one of your decisions against your accumulated pattern. Returns band_position (within_band/outlier) for 5 dimensions: decision_scale
• mcp-registry/com.hydrata/hydrata-mcp-server/start_simulation Start a flood simulation run for a built scenario. The scenario must be in 'built' status. Returns 202 with the new run. The run transition
• mcp-registry/ai.intuitek.the-stall/the-stall/content-moderation Classify text (and optional image URLs) for harmful content — hate speech, harassment, self-harm, sexual content, violence, and illicit inst
• mcp-registry/com.dropwatchhq/safe-check/counterfeit_risk Assess counterfeit RISK for a collectible listing (a risk SIGNAL, never proof of fake). Combines marketplace base-risk + a price-vs-retail-m
• mcp-registry/com.kernelcad/kernelcad/solve_sketch Use this when you need to solve a 2D sketch constraint set. Solve a 2D sketch constraint set. Side-effect-free: pass { entities, constraints
• mcp-registry/com.ezbizservices/social-media/score_engagement Score social media engagement for a brand or topic — engagement rate estimates, content type effectiveness, posting time analysis, and bench
• mcp-registry/ai.intuitek.the-stall/the-stall/polymarket-sentiment-shift Returns Polymarket prediction markets with the biggest recent probability shifts — useful for detecting sudden consensus changes on election
• mcp-registry/com.emergentphysicslab/waveguard/waveguard_compare Compare two data items for structural similarity using physics-based fingerprints. Returns cosine similarity (0–1) and Euclidean distance. U
• mcp-registry/com.predme/hypathesis/get_analysis_status Check the processing status of an uploaded paper. Poll this tool after uploading a PDF until status is 'Ready' before calling
• mcp-registry/com.emergentphysicslab/waveguard/waveguard_instability Estimate instability under controlled perturb-and-resolve trials.
• mcp-registry/com.geiant/mcp-perception/perception_embed [Sub-phase 4.2 — NOT YET IMPLEMENTED] Will generate Clay v1.5 embeddings.
• mcp-registry/com.claribi/mcp-server/get_analysis_status Check the status of a previously-dispatched run_analysis job. Returns the analysis result if completed.
• mcp-registry/com.run402.zhiji-signal/mcp/ji-sensing System of Thought Integration (SoTI) measurement — frozen/comfort/creative_edge zone detection.
• mcp-registry/ai.geodesiclabs/governance-platform/counterfactual Compare outcomes under different rule sets. Given the same data, runs trajectory analysis under two different sets of rules/co
• mcp-registry/ai.geodesiclabs/governance-platform/reject_rule Reject a discovered candidate rule so it will not be promoted into a Blueprint. Use after running discover_patterns when reviewing
• mcp-registry/ai.geodesiclabs/governance-platform/check_realization Run structural realization analysis on a payload. Embeds the payload via the Blueprint's declared embedding schema, projects i
• mcp-registry/ai.geodesiclabs/governance-platform/check_drift Check whether the data pattern has shifted since previous observations. Works with or without a Blueprint. Monitors structural sta
• mcp-registry/ai.gondola/gondola/predict_price Predict whether now is a good time to book a hotel, or if the user should wait for a better price. Uses historical price data and trend
• mcp-registry/com.queuesim/public/simulate_mmc Run a generic M/M/c queue simulation. Provide an arrival rate (λ, arrivals/hour), a service rate per server (μ, customers/hour each server c
• mcp-registry/com.queuesim/public/simulate_scenario Run one of the four preset scenarios (single, coffee, grocery, callcenter) with optional overrides. Overrides apply UNIFORMLY across open ho
• mcp-registry/com.queuesim/public/simulate_schedule Run a queueing simulation against an arbitrary 24-hour staffing schedule. Take this when the user describes a custom day shape that doesn't
• mcp-registry/ai.plith/plith/burnrate_track Log the actual cost of an LLM call after execution. Call this after every LLM request to build calibration data that improves burnrate_estim
• mcp-registry/com.queuesim/public/compare_separate_vs_pooled Run the classic operations-research teaching demo: pooled queueing (one shared queue, c servers) vs separate queues (c independent queues, o
• mcp-registry/com.queuesim/public/recommend_staffing INVERSE of simulate_mmc — given an arrival rate, service rate, and a target average wait time, returns the SMALLEST number of servers needed
• mcp-registry/com.queuesim/public/interpret_result Given an M/M/c configuration (arrivalRate, serviceRate, servers) and optionally an observed average wait, returns a queueing-theory framed i
• mcp-registry/com.sats4ai/bitcoin-ai-tools/colorize_image Colorize black-and-white or grayscale photos. DDColor (dual-decoder, ICCV 2023) — vivid, natural colorization. Impossible for text/vision LL
• mcp-registry/com.reliasim/public/run_buffer_tradeoff Buffer Tradeoff experiment — sweep a buffer's capacity from 50 → 10,000 units, measure throughput gain. Shows the diminishing-returns elbow
• mcp-registry/com.reliasim/public/run_showcase LIVE experiment — run a bottling-line demo against the real ReliaSim engine with parameters you choose, and get its verbatim run envelope (m
• mcp-registry/ai.intuitek.the-stall/the-stall/hf-model-search Search HuggingFace Hub for ML models. Specify a keyword (e.g. 'bert', 'llama', 'stable diffusion') and optional task filter (e.g. 'text-clas
• mcp-registry/com.100hires/100hires/hires_get_ai_score Get the structured AI score for an application, including per-criterion scores, justifications, and follow-up questions. Returns null score
• mcp-registry/com.danielsdesignstudio/mirror-ai-citability/score Return a brand's AI Citability Score (ACS, 0–100) and AEO/GEO/SEO sub-scores for a website — a fast, open check of how discoverable and cita
• mcp-registry/com.danielsdesignstudio/mirror-ai-citability/reflect_result Fetch the result of a Reflection started by the reflect tool. Pass the jobId that reflect returned. This tool LONG-POLLS: each call waits up
• mcp-registry/co.ainumbers/tools/detect_timeseries_anomalies Time-Series Anomaly Detector — OpenChainGraph compute node (risk_control). Runs deterministically in-browser; zero PII, zero egress. Exports
• mcp-registry/com.a3eecosystem.neurotrade/signal/generate_signal Generate an AI-powered crypto trading signal for a given pair and timeframe. Returns: action (OPEN_LONG | OPEN_SHORT | CLOSE), confidence (0
• mcp-registry/com.scanmalware.mcp/scanmalware-mcp/search_similar_scans Search for scans similar to a scan_id (paginated).
• mcp-registry/com.admitbase/admissions/calculate_match_score Given a user's GPA and test score, calculate match category (Safety/Target/Reach/Far Reach), admission probability, and percentiles for one
• mcp-registry/com.reliasim/public/run_gain_loss Gain/Loss experiment — disable each interrupt one at a time, measure production recovered. Reveals the ACTUAL impact of each failure mode (G
• mcp-registry/app.pulltrader/seller-economics/identify_card Resolve a natural-language trading-card description into structured fields (player/athlete, year, set, card number, parallel, grader, grade,
• mcp-registry/com.dropwatchhq/oracle/grade_card_centering Estimate a trading card's centering and rough PSA-style grade from a photo. NOTE: the centering measurement runs client-side in the browser
• mcp-registry/com.emergentphysicslab/waveguard/waveguard_multi_horizon_outlook Compute horizon-specific anomaly outlook and consistency across windows.
• mcp-registry/com.sats4ai/bitcoin-ai-tools/generate_text Generate text using frontier AI language models. Pure per-character pricing (no minimum): Kimi K2.5 (id=6, best, 100 chars/sat, 262K context
• mcp-registry/com.sats4ai/bitcoin-ai-tools/translate_text Translate text across 119 languages with high accuracy. Uses Qwen3-32B — multilingual transformer with strong low-resource language support.
• mcp-registry/app.cannonstudio/cannon-studio/estimate_generation_cost Estimate credits for a Cannon Studio generation request before creating billable work. Requires OAuth or a developer API key; it may update
• mcp-registry/com.sats4ai/bitcoin-ai-tools/list_models Discover available AI models with numeric IDs, tier labels, capabilities, and per-call pricing in sats. Call this before create_payment to f
• mcp-registry/com.sats4ai/bitcoin-ai-tools/detect_nsfw Classify image safety (normal / suggestive / explicit). Falcons.ai NSFW detection — 100x cheaper and faster than asking an LLM. Returns clas
• mcp-registry/com.sats4ai/bitcoin-ai-tools/detect_objects Detect and locate objects in an image by name. Grounding DINO (open-set detector, ECCV 2024) — describe what to find in natural language, ge
• mcp-registry/com.sats4ai/bitcoin-ai-tools/deblur_image Recover detail from camera-shake and accidental motion blur. NAFNet (ECCV 2022, SOTA on GoPro/SIDD benchmarks). Best for: handheld shake, bu
• mcp-registry/ai.geodesiclabs/governance-platform/geometric_confidence Compute a composite geometric confidence score from validation signals. No Blueprint required — works on any validate result.
• mcp-registry/ai.tunnelmind/data/sigil_score_weights Returns the active, versioned default weights used to combine an entity's trust-score components, plus the list of spec components that are
• mcp-registry/com.prooflayered/prooflayered/growth_bottleneck_scan Free passive scan of a public B2B SaaS website. Returns bottleneck scores (visibility, trust, conversion, scale), the primary public growth
• mcp-registry/com.gocreativeai.omnicall/agent-tools/ai_ask Returns frontier-quality LLM completion (DeepSeek V3.1 default; query ?model for gpt-5-mini, gemini-flash). Agents: summ Cost: $0.005–$0.05
• mcp-registry/com.babyblueviper/invinoveritas/decision Structured decision intelligence with confidence scoring. Provide a decision scenario and options; returns a JSON object with the recommende
• mcp-registry/com.gocreativeai.omnicall/agent-tools/ai_pro Returns Claude 4.5 Sonnet completion (query ?model for gpt-5, gpt-4o, gemini-pro, gemini-3.1-pro). Agents: complex analy Cost: $0.005–$0.05
• mcp-registry/com.gocreativeai.omnicall/agent-tools/ai_ultra Returns Claude Opus 4.6 completion—the top-end reasoning model for hardest tasks: deep multi-step analysis, synthesis, h Cost: $0.005–$0.05
• mcp-registry/ai.switchapp/switch/apply_iphone_realism Phone-shot amateur look — looks like a real person snapped it on their phone. Casual, candid, pore-level real, no professional gloss. Three
• mcp-registry/com.aidevboard/jobs/match_jobs Rank active AI/ML jobs against a candidate profile (skills, salary range, workplace, level). Scoring combines tag overlap (+2 per match), sa
• mcp-registry/ai.switchapp/switch/apply_movie_scene Put me in a movie — full cinematic film look matching specific film genres. Choose: neon-noir action thriller, 80s finance excess, comic-boo
• mcp-registry/ai.switchapp/switch/apply_high_fashion_editorial High-fashion magazine cover/editorial energy. Choose a photographer mood: Mario Testino glossy, Steven Klein dark cinematic, Inez & Vinoodh
• mcp-registry/ai.switchapp/switch/apply_graphic_editorial_portrait Sharp graphic editorial portrait — premium fashion-magazine grade, hard graphic composition. Classic studio or golden-hour outdoor.
• mcp-registry/ai.switchapp/switch/apply_ugc User-generated content — looks like a real person captured it casually. Choose: phone shot, film point-and-shoot, mirror selfie, or car self
• mcp-registry/com.aidesignblueprint/blueprint/architect.validate Pro/Teams — first-pass doctrine review of agentic code/workflow against the 10-principle Agentic AI Blueprint. ON CLIENT TIMEOUT — DO NOT RE
• mcp-registry/com.claribi/mcp-server/create_forecast Bind a forecast to a metric in your workspace. Stores the configuration, sets up the schedule, and resolves the source binding immediately s
• mcp-registry/com.claribi/mcp-server/run_forecast Run a forecast now. Reserves AI credits up front, dispatches the backtest + projection + correlation pipeline, and returns either the comple
• mcp-registry/com.kenoodl/synthesis/synthesis kenoodl surfaces the structural read your coding-agent run cannot reach from inside its own loop. Call it when retries stop producing: repea
• mcp-registry/ai.intuitek.the-stall/the-stall/document-qa-prep Prepares a document for question-answering and RAG pipelines. Chunks the input text at paragraph/sentence boundaries, assigns deterministic
• mcp-registry/com.kernelcad/kernelcad/solve_mates Use this when you need to solve the mate graph and get part poses. Run the v0.6 mate-graph solver on the active assembly. Returns { status,
• mcp-registry/ai.intuitek.the-stall/the-stall/huggingface-intel HuggingFace Hub intelligence: search AI models and datasets, get detailed model metadata, and find trending models by task. Returns download
• mcp-registry/com.kernelcad/kernelcad/evaluate_sdf Use this when you need to sample a signed-distance field at a point. Sample the signed distance from an in-script sdf.* field at a 3D point.
• mcp-registry/ai.intuitek.the-stall/the-stall/llm-proxy LLM inference proxy — pay USDC, get AI responses without managing API keys. Accepts a prompt and optional system instruction, forwards to Op
• mcp-registry/com.aurelianflo/core/compliance.queue.optimize Optimize a compliance review queue using current OFAC exact matches, future exposure forecast probabilities, exposure value, relationship ti
• mcp-registry/ai.intuitek.the-stall/the-stall/polymarket-accuracy-score Historical Polymarket crowd accuracy score: % of markets where the final crowd majority correctly predicted the outcome, plus Brier score (c
• mcp-registry/com.emergentphysicslab/waveguard/waveguard_wallet_profile Profile wallet behavior against baselines. Send normal wallet transaction patterns as training (tx_count, avg_value, unique_tokens, gas_spen
• mcp-registry/com.axiorank/axiorank/axiorank_author_detector Describe a risk in plain English and AxioRank's AI proposes a custom content detector (regex or keyword) and SAVES it DISABLED for your revi
• mcp-registry/ai.intuitek.the-stall/the-stall/vision-analyze Analyze any image URL using GPT-4o-mini vision. Returns structured analysis based on the mode: describe (full description), ocr (text extrac
• mcp-registry/com.axiorank/axiorank/axiorank_list_ml_assessments List your workspace's most recent ML/LLM threat assessments (model verdict, threat class, confidence, recommendation) for tool calls and car
• mcp-registry/ai.switchapp/switch/apply_cinematic_anamorphic ARRI Alexa anamorphic widescreen film look. Choose grade: warm golden, cool noir, or moody desaturated.
• mcp-registry/ai.compeller/compel/get_compel Get the current status, progress, and details of a Compeller generation job.
• mcp-registry/com.marketcheck/api/predict_price_with_comparables Predict car price along with comparable vehicles in the market. This provides predicted price, MSRP along with active set comparables to he
• mcp-registry/co.ainumbers/tools/build_agent_traffic_policy Agent-Traffic Acceptance Policy Builder — OpenChainGraph compute node (agent_guardrail_mandate). Runs deterministically in-browser; zero PII
• mcp-registry/com.memesio/meme-generator/get_template_ideas Turn a prompt into ranked meme template ideas.
• mcp-registry/com.wiselyenterprisesllc/x402-agent-payment-infrastructure/wisely_creator_catalog_recommend Recommend the next creator-catalog action for a subscriber situation, including fetch instructions or paid endpoint 402 probe instructions.
• mcp-registry/ai.com.mcp/openai-tools/retrieveModel Retrieves a model instance, providing basic information about the model such as the owner and permissioning.
• mcp-registry/com.claribi/mcp-server/get_forecast_trust Returns per-past-run accuracy for a forecast. Each row compares a prior run's projection against the actuals that have materialized since. U
• mcp-registry/co.ainumbers/tools/classify_dora_incident DORA Major-Incident Reporting Threshold Classifier — OpenChainGraph compute node (infrastructure_mandate). Runs deterministically in-browser
• mcp-registry/com.claribi/mcp-server/run_analysis Run a natural-language analytics question against your connected data sources. Consumes AI credits. Returns either the completed analysis re
• mcp-registry/com.claidex/failure-intelligence/run_statistical_analysis Run a statistical analysis computation. Supports: Wilson confidence intervals, binomial proportions, phase transition success rates, power c
• mcp-registry/com.readyapis/api/company_classify Classify a domain using the loaded curated company profile set.
• mcp-registry/com.civilquants/civilquants/compute_vehicle_restraint_system Paid tier only. Calling this without an authenticated CivilQuants account returns TIER_INSUFFICIENT — sign up at https://civilquants.com/pri
• mcp-registry/com.civilquants/civilquants/compute_anchored_wall Paid tier only. Calling this without an authenticated CivilQuants account returns TIER_INSUFFICIENT — sign up at https://civilquants.com/pri
• mcp-registry/co.ainumbers/tools/simulate_ict_cascade DORA ICT Cascade Simulator — OpenChainGraph compute node (infrastructure_mandate). Runs deterministically in-browser; zero PII, zero egress.
• mcp-registry/com.qsimhealth/public/recommend_md_count INVERSE of simulate_ed_demo — given an arrival rate and a target average wait, returns the smallest MD count meeting the target. Use when th
• mcp-registry/com.civilquants/civilquants/compute_cantilever_wall Free tier. Renders the MMHW standard only — CESMM4, NRM2 and SMM7 require a paid tier. Anonymous callers welcome. In-situ reinforced concret
• mcp-registry/com.reliastats/public/compute_availability Given MTBF and MTTR (same time unit), return steady-state availability A = MTBF / (MTBF + MTTR). One-line closed-form, but worth a dedicated
• mcp-registry/com.reliastats/public/recommend_distribution Given a free-text symptom description (e.g. 'manufacturing burn-in', 'bearing wearout under variable load', 'cosmic-ray bit flips'), return
• mcp-registry/co.ainumbers/tools/simulate_app_fraud_graph APP Fraud Graph Simulator — OpenChainGraph compute node (aml_rule). Runs deterministically in-browser; zero PII, zero egress. Exports an AP2
• mcp-registry/com.civilquants/civilquants/resolve_assembly_from_description Resolve a plain-English job description to candidate catalogue assemblies and the fields you'll need to compute one. Deterministic router —
• mcp-registry/com.crashstory/crashstory/compare_review_intelligence Compare AI-analyzed review intelligence across 2-5 law firms. Returns side-by-side pain point dimensions, sentiment, trust signals, response
• mcp-registry/ai.thinkneo/control-plane/thinkneo_policy_list List all active AI governance policies for your organization. Shows policy name, version, conditions, effect, and scope. Requires authentica
• mcp-registry/ai.thinkneo/control-plane/thinkneo_policy_evaluate Evaluate a request context against all active policies. Returns whether the request is allowed, which policies were violated, and what effec
• mcp-registry/ai.thinkneo/control-plane/thinkneo_policy_violations View policy violation history — which policies were triggered, by which agents, how many blocks/warnings/approvals occurred. Shows unresolve
• mcp-registry/co.ainumbers/tools/detect_transaction_anomalies Isolation Forest Transaction Anomaly Detector — OpenChainGraph compute node (risk_control). Runs deterministically in-browser; zero PII, zer
• mcp-registry/co.ainumbers/tools/score_credit_default_risk Credit Default Risk Scorer — OpenChainGraph compute node (credit_assessment). Regulatory deadline: 2026-08-02 (EU AI Act Annex III Part 5(b)
• mcp-registry/com.decision-anchor/da/get_environment_anomaly Observe environment-level anomaly distribution — within_band/outlier counts per dimension across the population. De-identified, k-anonymity
• mcp-registry/com.decision-anchor/da/get_self_classification_distribution Observe your self_classification distribution across your branch-1 decisions.
• mcp-registry/co.ainumbers/tools/score_tempo_validator_readiness Tempo Validator Readiness Scorer — OpenChainGraph compute node (infrastructure_mandate). Runs deterministically in-browser; zero PII, zero e
• mcp-registry/com.run402.llm-router/mcp/ji-sensing System of Thought Integration (SoTI) measurement — frozen/comfort/creative_edge zone detection.
• mcp-registry/com.scanmalware.mcp/scanmalware-mcp/get_ai_analysis Get AI analysis for a scan_id (if available).
• mcp-registry/co.ainumbers/tools/run_mcp_deployability_diagnostic MCP Server Deployability Diagnostic — OpenChainGraph compute node (agent_guardrail_mandate). Runs deterministically in-browser; zero PII, ze
• mcp-registry/co.ainumbers/tools/run_tempo_fit_diagnostic Tempo Fit Diagnostic — OpenChainGraph compute node (agent_guardrail_mandate). Runs deterministically in-browser; zero PII, zero egress. Expo
• mcp-registry/co.ainumbers/tools/score_aml_typologies AMLA Transaction-Typology Risk Scorer — OpenChainGraph compute node (risk_control). Regulatory deadline: 2027-07-01 (EU AMLR full applicatio
• mcp-registry/co.ainumbers/tools/run_arc_fit_diagnostic Arc Fit Diagnostic — OpenChainGraph compute node (agent_guardrail_mandate). Runs deterministically in-browser; zero PII, zero egress. Export
• mcp-registry/co.ainumbers/tools/model_arc_stablefx_rfq Arc StableFX RFQ Economics Model — OpenChainGraph compute node (treasury_mandate). Runs deterministically in-browser; zero PII, zero egress.
• mcp-registry/co.ainumbers/tools/run_agent_economy_fit Agent Economy Runtime Fit Diagnostic — OpenChainGraph compute node (agent_guardrail_mandate). Runs deterministically in-browser; zero PII, z
• mcp-registry/co.ainumbers/tools/run_ai_act_highrisk_fit EU AI Act High-Risk Fit & Classification Diagnostic — OpenChainGraph compute node (agent_guardrail_mandate). Runs deterministically in-brows
• mcp-registry/co.ainumbers/tools/build_ai_conformity_pack AI Act Conformity Pack Builder — OpenChainGraph compute node (model_governance). Runs deterministically in-browser; zero PII, zero egress. E
• mcp-registry/co.ainumbers/tools/classify_agentic_ai_risk Agentic AI Risk & GPAI Governance Classifier — OpenChainGraph compute node (model_governance). Runs deterministically in-browser; zero PII,
• mcp-registry/co.ainumbers/tools/predict_settlement_fail Settlement-Fail Predictor — OpenChainGraph compute node (model_governance). Runs deterministically in-browser; zero PII, zero egress. Export
• mcp-registry/co.ainumbers/tools/model_buy_in_exposure Buy-In Exposure Modeler — OpenChainGraph compute node (compliance_mandate). Runs deterministically in-browser; zero PII, zero egress. Export
• mcp-registry/co.ainumbers/tools/compute_settlement_efficiency_kpi Settlement Efficiency KPI Engine — OpenChainGraph compute node (model_governance). Runs deterministically in-browser; zero PII, zero egress.
• mcp-registry/co.ainumbers/tools/classify_blockchain_quantum_risk Blockchain / Stablecoin Quantum-Risk Classifier — OpenChainGraph compute node (model_governance). Runs deterministically in-browser; zero PI
• mcp-registry/co.ainumbers/tools/score_fuzzy_match_calibration Fuzzy-Match Calibration Scorer — OpenChainGraph compute node (model_governance). Runs deterministically in-browser; zero PII, zero egress. E
• mcp-registry/co.ainumbers/tools/run_mica_casp_fit MiCA CASP Fit Diagnostic — OpenChainGraph compute node (agent_guardrail_mandate). Runs deterministically in-browser; zero PII, zero egress.
• mcp-registry/co.ainumbers/tools/score_partner_stablecoin_readiness Arc Partner Stablecoin Onboarding Conformance — OpenChainGraph compute node (compliance_mandate). Runs deterministically in-browser; zero PI
• mcp-registry/co.ainumbers/tools/assess_suspect_product_status DSCSA Suspect/Illegitimate Product Quarantine Assessor — OpenChainGraph compute node (compliance_mandate). Runs deterministically in-browser
• mcp-registry/co.ainumbers/tools/verify_product_authenticity Luxury Goods Product Authenticity Verifier — OpenChainGraph compute node (compliance_mandate). Runs deterministically in-browser; zero PII,
• mcp-registry/co.ainumbers/tools/validate_fsma204_cte FSMA 204 Critical Tracking Event (CTE) Validator — OpenChainGraph compute node (compliance_mandate). Runs deterministically in-browser; zero
• mcp-registry/co.ainumbers/tools/generate_zk_compliance_proof ZK Compliance Proof Generator — OpenChainGraph compute node (compliance_mandate). Runs deterministically in-browser; zero PII, zero egress.
• mcp-registry/dev.gemot/gemot/analyze Analyze disagreements and find common ground. Actions: - run: Trigger analysis — extracts cruxes, clusters, consensus (deliberation_id; opti
• mcp-registry/cn.whylingxi/insurance/check_underwriting 核保预判：根据用户健康状况，评估各产品的可投保性（可正常投保/需加费除外/可能拒保）。
• mcp-registry/dev.metamesh-uga/metamesh-uga/openai OpenAI API integration
• mcp-registry/io.github.0580iris-lang/x711-gas-station/x711_social_oracle Crypto social sentiment — narrative pulse, hype velocity, community data via CoinGecko + DexScreener. Returns real-time sentiment score, tre
• mcp-registry/io.github.br0ski777/ai-summarizer/ai_summarize_text Use this when you need to summarize long text into concise key points. Returns a structured summary with bullet points and reading metrics.
• mcp-registry/io.github.deesmo/arch-tools-mcp/extract-entities Named entity recognition: people, organizations, locations, dates, money, and more
• mcp-registry/io.github.deesmo/arch-tools-mcp/ocr-extract Extract text from images or screenshots using AI vision (base64 or URL input)
• mcp-registry/io.github.foundrynet/foundrynet-inference/chat LLM inference proxy (Claude). $0.02/call.
• mcp-registry/io.github.jcjamet/ia-qa-toolbox/detect_language Detect the natural language of a text using n-gram frequency analysis and common word markers. Supports 15 languages: English, French, Spani